DOI QR코드

DOI QR Code

Hybrid Multi-agent Learning Strategy

혼성 다중에이전트 학습 전략

  • Kim, Byung-Chun (Dept. of Computer&Web Information Engineering, HanKyung National University) ;
  • Lee, Chang-Hoon (Dept. of Computer&Web Information Engineering, HanKyung National University)
  • 김병천 (국립한경대학교 컴퓨터웹정보공학과) ;
  • 이창훈 (국립한경대학교 컴퓨터웹정보공학과)
  • Received : 2013.11.19
  • Accepted : 2013.12.13
  • Published : 2013.12.31

Abstract

In multi-agent systems, How to coordinate the behaviors of the agents through learning is a very important problem. The most important problems in the multi-agent system are to accomplish a goal through the efficient coordination of several agents and to prevent collision with other agents. In this paper, we propose a novel approach by using hybrid learning strategy. It is used hybrid learning strategy to control the multi-agent system efficiently by using the spatial relationship among the agents. Through experiments, we can see approximate faster the goal then other strategies and avoids collision among the agents.

다중 에이전트 시스템에서 학습을 통해 여러 에이전트들의 행동을 어떻게 조절할 것인가는 매우 중요한 문제이다. 가장 중요한 문제는 여러 에이전트가 서로 효율적인 협동을 통해 목표를 성취하는 것과 다른 에이전트들과 충돌을 방지하는 것이다. 본 논문에서는 혼성 학습 전략을 제안하였다. 제안된 방법은 다중에이전트를 효율적으로 제어하기 위해 에이전트들 사이의 공간적 관계를 이용하였다. 실험을 통해 제안된 방법은 에이전트들과 충돌을 피하면서 에이전트들의 목표에 빠르게 수렴함을 알 수 있었다.

Keywords

References

  1. Peter Stone, Manuela Veloso, Multi-agent system : "A Survey from a Machine Learning", Technical Report CMU-CS-97-193, The University of Carnegies Mellon, December, 4, 1997.
  2. Sandip Sen, Mahendra Seckaran, "Multi-agent coordination with learning classifier system", In Proceeding of the AAAI 99 Worshop on Negotiation, pp.44-49, 1999.
  3. Claus, C. and C. Boutilier, 1998. The dynamics of reinforcement learning in coorperative multiagent systems. Proceeding of AAAI-98, pp. 746-752.
  4. R.S. Sutton and A.G. Barto, Reinforcement Learning : An Introduction, MIT Press, 1998.
  5. C. Guestrin, M.Lagoudakis and R. Parr. "Coordinated reinforcement learning", In Proc. of th 19th International Conference on machine Learning, 2002.
  6. L.M. Sephens and M.B. Merx, "The effect of agent control strategy on the performance of a DAI pursuit problem", In Proceeding of the 1990, Distributed AI Workshop, October, 1990.
  7. A. G. Barto and D.A. White and D.A. Sofge, "Reinforcement Learning with less data and less real time", Machine Learning, 13, pp.103-130, 1993.
  8. C.J.C.H. Watkins, "Technical note : Q-learning", Machine Learning, 8, pp. 279-292, 1989.
  9. M.Benda, V. Jagannathan and R.Dodhiawala, "On optimal cooperation of knowledge source an empirical investigation", Technical Reoprt BCS-G2010-28, Boeing Advanced Technology Center, Boeing Computing Services, Seattle, Washington, July, 1986.